Find code blind spots with independent AI reviews.
Synthesizes independent model reviews of code changes into a prioritized verdict with reasons for accepting or dismissing findings.
When to use it
Use when asked for an adversarial or multi-model review, to challenge code, or to find blind spots.
Give it code changes to review; it returns a synthesized verdict without automatically applying changes.
What you provide
Requires consulting poteto-mode to choose each reviewer's reasoning level; its platform mappings are also required on the named alternative agents.
This skill
interrogate
Proposes changes to reviewer defaults